Application of MR morphologic, diffusion tensor, and perfusion imaging in the classification of brain tumors using machine learning scheme.

PURPOSE: While MRI is the modality of choice for the assessment of patients with brain tumors, differentiation between various tumors based on their imaging characteristics might be challenging due to overlapping imaging features. The purpose of this study was to apply a machine learning scheme using basic and advanced MR sequences for distinguishing different types of brain tumors. METHODS: The study cohort included 141 patients (41 glioblastoma, 38 metastasis, 50 meningioma, and 12 primary central nervous system lymphoma). A computer-assisted classification scheme, combining morphologic MRI, perfusion MRI, and DTI metrics, was developed and used for tumor classification. The proposed multistep scheme consists of pre-processing, ROI definition, features extraction, feature selection, and classification. Feature subset selection was performed using support vector machines (SVMs). Classification performance was assessed by leave-one-out cross-validation. Given an ROI, the entire classification process was done automatically via computer and without any human intervention. RESULTS: A binary hierarchical classification tree was chosen. In the first step, selected features were chosen for distinguishing glioblastoma from the remaining three classes, followed by separation of meningioma from metastasis and PCNSL, and then to discriminate PCNSL from metastasis. The binary SVM classification accuracy, sensitivity and specificity for glioblastoma, metastasis, meningiomas, and primary central nervous system lymphoma were 95.7, 81.6, and 91.2%; 92.7, 95.1, and 93.6%; 97, 90.8, and 58.3%; and 91.5, 90, and 96.9%, respectively. CONCLUSION: A machine learning scheme using data from anatomical and advanced MRI sequences resulted in high-performance automatic tumor classification algorithm. Such a scheme can be integrated into clinical decision support systems to optimize tumor classification.

Gaussian bandwidth selection for manifold learning and classification.

Kernel methods play a critical role in many machine learning algorithms. They are useful in manifold learning, classification, clustering and other data analysis tasks. Setting the kernel's scale parameter, also referred to as the kernel's bandwidth, highly affects the performance of the task in hand. We propose to set a scale parameter that is tailored to one of two types of tasks: classification and manifold learning. For manifold learning, we seek a scale which is best at capturing the manifold's intrinsic dimension. For classification, we propose three methods for estimating the scale, which optimize the classification results in different senses. The proposed frameworks are simulated on artificial and on real datasets. The results show a high correlation between optimal classification rates and the estimated scales. Finally, we demonstrate the approach on a seismic event classification task.

Unsupervised tumor detection in Dynamic PET/CT imaging of the prostate.

Early detection and localization of prostate tumors pose a challenge to the medical community. Several imaging techniques, including PET, have shown some success. But no robust and accurate solution has yet been reached. This work aims to detect prostate cancer foci in Dynamic PET images using an unsupervised learning approach. The proposed method extracts three feature classes from 4D imaging data that include statistical, kinetic biological and deep features that are learned by a deep stacked convolutional autoencoder. Anomalies, which are classified as tumors, are detected in feature space using density estimation. The proposed algorithm generates promising results for sufficiently large cancer foci in real PET scans imaging where the foci is not viewed by the tomographic devices used for detection.

Analysis of Human Brain Structure Reveals that the Brain "Types" Typical of Males Are Also Typical of Females, and Vice Versa.

Findings of average differences between females and males in the structure of specific brain regions are often interpreted as indicating that the typical male brain is different from the typical female brain. An alternative interpretation is that the brain types typical of females are also typical of males, and sex differences exist only in the frequency of rare brain types. Here we contrasted the two hypotheses by analyzing the structure of 2176 human brains using three analytical approaches. An anomaly detection analysis showed that brains from females are almost as likely to be classified as "normal male brains," as brains from males are, and vice versa. Unsupervised clustering algorithms revealed that common brain "types" are similarly common in females and in males and that a male and a female are almost as likely to have the same brain "type" as two females or two males are. Large sex differences were found only in the frequency of some rare brain "types." Last, supervised clustering algorithms revealed that the brain "type(s)" typical of one sex category in one sample could be typical of the other sex category in another sample. The present findings demonstrate that even when similarity and difference are defined mathematically, ignoring biological or functional relevance, sex category (i.e., whether one is female or male), is not a major predictor of the variability of human brain structure. Rather, the brain types typical of females are also typical of males, and vice versa, and large sex differences are found only in the prevalence of some rare brain types. We discuss the implications of these findings to studies of the structure and function of the human brain.